© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 5830
    Prev
    Next
    INDEX
    Explanations

    why it's

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_22_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     also
    0.70
    odie
    0.66
     both
    0.65
    }\\
    0.64
    /).
    0.62
     current
    0.61
     होण्याची
    0.60
    wnież
    0.60
    рып
    0.60
     Dorothe
    0.59
    POSITIVE LOGITS
    fits
    0.85
     établi
    0.82
    पांच
    0.82
    prés
    0.80
    ટ્સ
    0.80
    exists
    0.78
     cinque
    0.77
    ಉ
    0.76
     rés
    0.76
     বজ
    0.75
    Activations Density 0.037%

    No Known Activations